135 lines
4.8 KiB
Plaintext
135 lines
4.8 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "609b9e9d-7f2b-49c3-b08f-97e6e5259242",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdin",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Enter the professor's name: Ali Asadpour\n",
|
|
"Enter your research topic: AI in architecture\n",
|
|
"Enter your name: Masih Moafi\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"C:\\Users\\Josep\\anaconda3\\envs\\myenv\\lib\\site-packages\\transformers\\generation\\configuration_utils.py:492: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.7` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\n",
|
|
" warnings.warn(\n",
|
|
"C:\\Users\\Josep\\anaconda3\\envs\\myenv\\lib\\site-packages\\transformers\\generation\\configuration_utils.py:497: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"Generated Email:\n",
|
|
"\n",
|
|
"Dear Professor Ali Asadpour,\n",
|
|
"\n",
|
|
" I am writing to express my interest in pursuing research under your guidance. My research topic revolves around AI in architecture.\n",
|
|
"\n",
|
|
" I believe that your work in this area is groundbreaking, and I am eager to contribute to your ongoing projects.\n",
|
|
"\n",
|
|
" Best regards,\n",
|
|
" Masih Moafi\n",
|
|
" _________________________________________\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from transformers import AutoModelForCausalLM, AutoTokenizer\n",
|
|
"\n",
|
|
"# Load the tokenizer and model for GPT-J\n",
|
|
"tokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-j-6B\")\n",
|
|
"model = AutoModelForCausalLM.from_pretrained(\"EleutherAI/gpt-j-6B\")\n",
|
|
"\n",
|
|
"def generate_email(professor_name, research_topic, user_name):\n",
|
|
" \"\"\"\n",
|
|
" Generate a professional and customizable email using GPT-J.\n",
|
|
" Args:\n",
|
|
" professor_name (str): The professor's name.\n",
|
|
" research_topic (str): The user's research topic.\n",
|
|
" user_name (str): The user's name.\n",
|
|
" Returns:\n",
|
|
" str: The generated email text.\n",
|
|
" \"\"\"\n",
|
|
" # Email template\n",
|
|
" prompt = f\"\"\"\n",
|
|
" Dear Professor {professor_name},\n",
|
|
"\n",
|
|
" I am writing to express my interest in pursuing research under your guidance. My research topic revolves around {research_topic}.\n",
|
|
"\n",
|
|
" I believe that your work in this area is groundbreaking, and I am eager to contribute to your ongoing projects.\n",
|
|
"\n",
|
|
" Best regards,\n",
|
|
" {user_name}\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" # Encode input\n",
|
|
" input_ids = tokenizer.encode(prompt, return_tensors=\"pt\")\n",
|
|
"\n",
|
|
" # Generate email with controlled randomness\n",
|
|
" output = model.generate(\n",
|
|
" input_ids,\n",
|
|
" max_length=len(input_ids[0]) + 100, # Slightly extend length to avoid truncation\n",
|
|
" do_sample=False, # Disable sampling for deterministic output\n",
|
|
" temperature=0.7, # Control output randomness\n",
|
|
" top_p=0.9, # Use nucleus sampling for coherent generation\n",
|
|
" pad_token_id=tokenizer.eos_token_id # Prevent padding issues\n",
|
|
" )\n",
|
|
"\n",
|
|
" # Decode and return the text\n",
|
|
" generated_email = tokenizer.decode(output[0], skip_special_tokens=True)\n",
|
|
" return generated_email.strip()\n",
|
|
"\n",
|
|
"# Input data\n",
|
|
"professor_name = input(\"Enter the professor's name: \")\n",
|
|
"research_topic = input(\"Enter your research topic: \")\n",
|
|
"user_name = input(\"Enter your name: \")\n",
|
|
"\n",
|
|
"# Generate and print the email\n",
|
|
"email = generate_email(professor_name, research_topic, user_name)\n",
|
|
"print(\"\\nGenerated Email:\\n\")\n",
|
|
"print(email)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f575bf56-5146-49df-803a-f1ceecdbc963",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.8.19"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|